VERSIL91 commited on
Commit
bd2f297
·
verified ·
1 Parent(s): 4153657

Training in progress, step 20, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73911326e456203d756947faff0cd28637f8c4407f111f1beffb103de23b8723
3
  size 6804608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bbb68bf2fb1f6c4e9d08ac497dbdf14e1285d6fb9112f6bf573511e716e6bde
3
  size 6804608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fd9a3692c39d4995c775f1ccede45a0e5ee6163a4b3be2fa4185e66cf56cf61
3
  size 3633466
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b802cbe9dc1f55d41c2886037156e76f2ccdce551b1af42f2d3b285cdcdcea59
3
  size 3633466
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ea24ba22f005ab5531315a7c25fe17ce3b0d82d32e4d057cd4a8d9beeaa0eb4
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.025660215973484442,
5
  "eval_steps": 5,
6
- "global_step": 15,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -144,6 +144,49 @@
144
  "eval_samples_per_second": 254.275,
145
  "eval_steps_per_second": 127.267,
146
  "step": 15
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
147
  }
148
  ],
149
  "logging_steps": 1,
@@ -158,12 +201,12 @@
158
  "should_evaluate": false,
159
  "should_log": false,
160
  "should_save": true,
161
- "should_training_stop": false
162
  },
163
  "attributes": {}
164
  }
165
  },
166
- "total_flos": 205755902853120.0,
167
  "train_batch_size": 2,
168
  "trial_name": null,
169
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.03421362129797926,
5
  "eval_steps": 5,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
144
  "eval_samples_per_second": 254.275,
145
  "eval_steps_per_second": 127.267,
146
  "step": 15
147
+ },
148
+ {
149
+ "epoch": 0.027370897038383406,
150
+ "grad_norm": 0.5180953741073608,
151
+ "learning_rate": 3.4549150281252636e-05,
152
+ "loss": 3.3701,
153
+ "step": 16
154
+ },
155
+ {
156
+ "epoch": 0.02908157810328237,
157
+ "grad_norm": 0.4908219873905182,
158
+ "learning_rate": 2.061073738537635e-05,
159
+ "loss": 3.3523,
160
+ "step": 17
161
+ },
162
+ {
163
+ "epoch": 0.030792259168181332,
164
+ "grad_norm": 0.5021977424621582,
165
+ "learning_rate": 9.549150281252633e-06,
166
+ "loss": 3.2482,
167
+ "step": 18
168
+ },
169
+ {
170
+ "epoch": 0.03250294023308029,
171
+ "grad_norm": 0.4103702902793884,
172
+ "learning_rate": 2.4471741852423237e-06,
173
+ "loss": 3.1689,
174
+ "step": 19
175
+ },
176
+ {
177
+ "epoch": 0.03421362129797926,
178
+ "grad_norm": 0.42450156807899475,
179
+ "learning_rate": 0.0,
180
+ "loss": 3.017,
181
+ "step": 20
182
+ },
183
+ {
184
+ "epoch": 0.03421362129797926,
185
+ "eval_loss": 3.317256212234497,
186
+ "eval_runtime": 3.8839,
187
+ "eval_samples_per_second": 253.609,
188
+ "eval_steps_per_second": 126.933,
189
+ "step": 20
190
  }
191
  ],
192
  "logging_steps": 1,
 
201
  "should_evaluate": false,
202
  "should_log": false,
203
  "should_save": true,
204
+ "should_training_stop": true
205
  },
206
  "attributes": {}
207
  }
208
  },
209
+ "total_flos": 274341203804160.0,
210
  "train_batch_size": 2,
211
  "trial_name": null,
212
  "trial_params": null